EXPLORING DEEP NEURAL NETWORKS FOR DISTORTION MODELING IN ELECTRIC GUITAR SIGNALS

Vol 56, 2024 - 310097
Poster formatting rules (PS)
Favorite this paper
How to cite this paper?
Abstract

This study investigated the ability of MLP and LSTM networks to model distortions in electric guitar signals. Both architectures were trained and evaluated using quantitative metrics, including Mean Square Error (NDE) and Kolmogorov-Smirnov Test (KS), as well as Cumulative Distribution Function (ADF) analysis. The results revealed that both networks accurately reproduced the distortion effects, with low error and high statistical similarity between the generated signals and the original ones. This highlights the effectiveness of the proposed approaches and suggests a number of practical applications for these techniques, from enhancements in audio processors to the development of more sophisticated guitar effects simulators. All in all, this study represents a significant breakthrough in audio effects modeling, opening up new perspectives for innovation in areas related to music and technology.

Share your ideas or questions with the authors!

Did you know that the greatest stimulus in scientific and cultural development is curiosity? Leave your questions or suggestions to the author!

Sign in to interact

Have a question or suggestion? Share your feedback with the authors!

Institutions
  • 1 Universidade Federal de Goiás
Track
  • 11. IC – Computational Intelligence
Keywords
Deep Learning
Neural Networks
Audio Modeling